facebookresearch/maskrcnn-benchmark
GitHub で見るInference time increases linearly with batch size
Open
#294 opened on 2018年12月20日
help wanted
説明
❓ Questions and Help
I tested the batch inference,this is result batch size time 1 0.22 2 0.42 4 0.84 6 1.2 8 crash OOM Why big batchsize doesn't save time?